Kuis terkait panduan · Keras Tingkat

Echo State Networks dan Kuis Komputasi Reservoir

Memeriksa dinamika reservoir tetap, pembacaan terlatih, memori memudar, radius spektral, dan perhitungan di balik prediksi reservoir.

Jalur panduan terkaitJaringan Echo State dan Komputasi Reservoir
Pertanyaan 1 dari 8

Di Echo State Network, beban manakah yang sebenarnya dilatih?

Pratinjau setiap pertanyaan8 pertanyaan

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

  1. Di Echo State Network, beban manakah yang sebenarnya dilatih?
    • Hanya bobot keluaran (pembacaan).
    • Semua bobot berulang di dalam reservoir
    • Hanya bobot masukan
    • Tidak ada beban yang pernah dilatih
  2. Which condition expresses the echo state property for two runs with the same input history?
    • Their recurrent weights must all be trained by backpropagation
    • Their reservoir states eventually become independent of different initial states
    • Their output weights must have spectral radius exactly one
    • Their hidden states must equal the raw input at every step
  3. Mengapa pelatihan ESN jauh lebih cepat dibandingkan pelatihan LSTM standar?
    • ESN tidak menggunakan neuron sama sekali
    • ESN hanya berjalan di komputer kuantum
    • ESN menghindari propagasi mundur sepanjang waktu dengan hanya menyelesaikan pembacaan linier
    • ESN tidak memerlukan data input
  4. How is spectral radius commonly used when tuning an echo-state reservoir?
    • It directly sets the number of readout classes
    • It guarantees fading memory for every recurrent matrix
    • It measures the number of trainable reservoir weights
    • It is a recurrent-feedback scale heuristic for balancing rich dynamics and stability, not a complete guarantee of the echo state property
  5. Liquid State Machines, suatu bentuk komputasi reservoir spiking-neuron, diperkenalkan oleh siapa?
    • Wolfgang Maass
    • Geoffrey Hinton
    • Andrew Ng
    • Yosua Bengio
  6. What does the fixed reservoir compute before the ESN readout produces an output?
    • A normalized probability over all possible weights
    • A high-dimensional dynamic state representation of recent inputs
    • A learned transition table for every future sequence
    • A separate trained policy for each output class
  7. What method is commonly used to fit an Echo State Network’s readout weights?
    • Backpropagation through all fixed recurrent weights
    • Dynamic routing by agreement
    • Linear least-squares regression, often with ridge regularization
    • A softmax over reservoir eigenvalues
  8. What does the spectral radius of a recurrent weight matrix mean?
    • The sum of all matrix entries
    • The number of nonzero output weights
    • The average magnitude of the input sequence
    • The largest absolute value among its eigenvalues